G
Geoffrey E. Hinton
Researcher at Google
Publications - 426
Citations - 501778
Geoffrey E. Hinton is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Generative model. The author has an hindex of 157, co-authored 414 publications receiving 409047 citations. Previous affiliations of Geoffrey E. Hinton include Canadian Institute for Advanced Research & Max Planck Society.
Papers
More filters
Journal ArticleDOI
Learning distributed representations of concepts using linear relational embedding
TL;DR: In this paper, linear relational embedding is introduced as a means of learning a distributed representation of concepts from data consisting of binary relations between these concepts, and the operation of applying a relation to a concept as a matrix-vector multiplication that produces an approximation to the related concept is learned by maximizing an appropriate discriminative goodness function using gradient ascent.
Journal ArticleDOI
Two Distributed-State Models For Generating High-Dimensional Time Series
TL;DR: A model based on the restricted Boltzmann machine (RBM) that uses an undirected model with binary latent variables and real-valued "visible" variables that can capture diverse styles of motion with a single set of parameters and introduces multiplicative three-way interactions.
Proceedings Article
A Better Way to Pretrain Deep Boltzmann Machines
TL;DR: A different method of pretraining DBMs is developed that distributes the modelling work more evenly over the hidden layers and demonstrates that the new pretraining algorithm allows us to learn better generative models.
Book ChapterDOI
Generating Facial Expressions with Deep Belief Nets
TL;DR: This chapter introduces a novel approach to learning to generate facial expressions that uses a deep belief net and demonstrates this by restricting it to generate expressions with a given identity and with elementary facial expressions such as “raised eyebrows.”